In push for more efficient AI, Korean researchers develop dual-output artificial synapse

Researchers at Korea University have developed a dual-output artificial synapse designed to improve the energy efficiency of multitasking artificial intelligence (AI) systems, the university said Monday. The research was led by professors Wang Gun-uk and Park Young-ran of the KU-KIST Graduate School of Converging Science and Technology, a joint program established by Korea University and the Korea Institute of Science and Technology. The human brain carries out many tasks at once, processing a stream of signals in parallel with remarkable efficiency. Conventional AI chips, in contrast, are typically built for narrowly defined functions. As a result, juggling multiple operations often requires breaking computations into separate parts or running them in sequence — a design that can sharply increase power consumption. Replicating the brain’s capability has become a growing focus in AI research as systems require increasing amounts of computing power and electricity. The KU-KIST team created a brain-inspired artificial synapse that emits both electrical and optical signals simultaneously,

Read Full Article